STA 402/502 TERM PROJECT DESCRIPTION
Overview. Project work focuses on drawing data from complicated sources to prepare a new data set that is
ready for a statistical analysis. Projects are programming intensive and use computational tools discussed in
class, found in the text, or included in SAS.
Students are given a list of general topic areas from which data sets will be assigned. The instructor then assigns
a specific collection of data sets and a project task to each student. Project tasks consist of obtaining, cleaning,
extracting, transforming, combining and displaying data sets.
Four project phases (100 points, for 25% of the course grade)
See the course syllabus and Canvas assignments for timeline and due dates.
Project selection (4 points). Please complete the online survey to indicate the general topic area of the
available course data sets that you would like to work with. Within a few days, the instructor will provide you
with access to your assigned data sets and an assigned task that you will complete for your project.
Grading rubric for project selection phase: 4 points – Full credit for completing the survey.
Progress update (16 points). Please submit:
• Your current project SAS code as a SAS program file (*.sas).
• A PDF document containing the following material organized in this order:
1. Your name, class section, and the original statement from the instructor of your assigned task.
2. Progress report [2-4 pages] including a description of your project progress so far, your plans for
proceeding, and questions to the instructor on how to proceed. Please include enough detail
that the instructor can understand what you've done and can provide guidance on moving
forward with your project.
3. Example graphs and/or tables produced by your code, if any.
4. Your current SAS code.
Grading rubric for progress update phase:
4 points – PDF file organization (see above).
12 points – Code in progress. Full credit for submitting code that’s relevant to the project.
Preliminary review (32 points). By this stage you are expected to have completed the core aspects of data
input, preparation and display that underlie your assigned task. (It’s okay if you still have work left to do on code
flexibility, code documentation, redundant/repetitive code, or refining graphs/tables.) Please submit:
• Your current project SAS code as a SAS program file (*.sas file).
• A PDF document containing the following material organized in this order:
1. Your name, class section, and the original statement from the instructor of your assigned task.
2. Tables and graphs produced by your code, with up to 2 pages of narrative explanation of the
displays. Please write this section so that it can be understood by another STA 402/502 student
who is not familiar with your assigned data set or your code.
3. Plans for completing the project and questions (if any) to the instructor.
4. Your current SAS code.
Grading rubric for preliminary review phase:
4 points – PDF file organization (see above).
p.2
8 points – Graphs and/or tables.
Grading Criteria: Do the displays address the core aspects of the assigned task?
Excellent Good In progress A Start
8 points 7 points 6-5 points 4-3 points 0 points
Task displays are
appropriately
annotated.
Includes examples of
all displays required
for task.
Some displays for
task are present and
others are lacking.
Displays show data
set features, but do
not address task.
None
included.
20 points – Code completeness.
Grading criteria: Are the core aspects of data input, preparation and display complete for the assigned
task?
Excellent Good In progress A start
20 points 19-17 points 16-14 points 13-11 points 0 points
Assigned coding task
is nearly complete.
Core aspects of task
code are ready,
except for minor
issues and code
flexibility.
Data input and
preparation done,
but still need to
address some key
subtasks.
Data input and
preparation tasks
not yet completed
or correct.
None
included.

Final submission (48 points). To complete the project, the graphs and tables produced by your code
should be carefully constructed and annotated. Your SAS program(s) should include all code needed for data
input, data preparation, tables and graphs per the assigned task. Your code should be fully documented and
structured for readability, use macros where appropriate, and include no redundant or repetitive code. Please
submit:
• Your final documented SAS code as SAS program file(s), packaged according to the instructions on the
final page of this document.
• A PDF document containing the following material organized in this order:
1. Your name, class section, and the original statement from the instructor of your assigned task.
2. Tables and graphs produced by your code to demonstrate that the assigned task has been
completed, with narrative explanation of the displays. Please write this section so that it can be
understood by another STA 402/502 student who is not familiar with your assigned data set or
your code.
3. Your final documented SAS code.
Grading rubric for final submission:
4 points – PDF file organization (see above).
8 points – Code presentation.
Grading criteria: Is the code easy to understand? Is documentation appropriate? Is repetitive and
unnecessary code avoided?
Excellent Good In progress A Start
8 points 7 points 6-5 points 4-3 points 0 points
Thorough, accurate
comments. Elegant,
efficient code.

No unnecessary
code. Easy to read.
Good commenting,
formatting, and
object names.
Sparse comments
or awkward
formatting.
Redundant or
repetitive code.
Few comments.
Difficult to
understand what is
being attempted.
Bare
code.


p.3
8 points – Code correctness.
Grading Criteria: Does the code run correctly and produce the displays required by the assigned task?
Excellent Good In progress A Start
8 points 7 points 6-5 points 4-3 points 0 points
Coding solution
provides extra value
beyond task (such as
speed, storage use,
robustness, etc.)
Code runs correctly
and produces the
required displays.
Code is complete
but cannot be run
without errors or
some modification.
Code is incomplete
and does not
address core tasks.
No code.
8 points – Code flexibility.
Grading criteria: Do macros provide the flexibility required by the assigned task?
Excellent Good In progress A Start
8 points 7 points 6-5 points 4-3 points 0 points
Macros provide
useful flexibility
beyond assigned
task.
Macros provide
requested flexibility.
Some flexibility
implemented, but
not fully addressing
assigned task.
Mere existence of
macro code or
macro variables.
None
included.
8 points – Graphs and/or Tables.
Grading Criteria: Are displays well designed and appropriately annotated?
Excellent Good In progress A Start
8 points 7 points 6-5 points 4-3 points 0 points
Creative displays
that yield strong
insights.
Well-designed and
appropriately
annotated displays.
Some displays or
annotations
awkward.
Unsuitable displays
and annotations.
None
included.
6 points – Overall Project Execution.
Grading criteria: Is the solution appropriate in complexity and scope?
Excellent Good In progress A Start
6 points 5 points 4-3 points 2-1 points 0 points
Task addressed
innovatively or
independently.
Appropriate
approach and effort.
Some important
gaps in approach or
effort.
Weak effort.
Lightweight or
unsuitable
approach.
No sub-
mission.
6 points – Responsiveness to instructor feedback.
Grading criteria: Were the instructor’s comments and suggestions on coding and draft report suitably
addressed by the end?
Excellent Good In progress
6 points 5-4 points 3-2 points 0 points
All comments and suggestions
fully addressed or resolved.
Or no suggestions were needed
during the preliminary review.
Major comments and
suggestions addressed
or resolved, but some
minor items not
addressed.
Some major comments
and suggestions not
adequately addressed.
No major
suggestions
or comments
addressed.



p.4
Project Code Preparation for Final Submission
The instructor will run your final SAS code to make sure that it works without errors, that it works for other
parameter choices made by the instructor, and that it creates output matching the output shown in your report.
Please include a detailed header comment block at the beginning of your main SAS file indicating what the
program does and giving clear instructions on how to use the code. The instructions in your header comments
should:
A. Explain the method by which the instructor can run your code to set things up, if this requires a
separate action.
B. Explain how, after the setup actions, to invoke the macro(s) by which the user makes selections
according to the specifications of your assigned task.
C. Provide, as examples, the particular macro invocations needed to create the output shown in your
report.
The instructor will place your submitted SAS file(s) (with *.sas extensions) in a folder that also contains copies of
the datasets that you originally found in your assigned Google Drive folder. Please organize your macro SAS file
so that the instructor can use one of the following two methods to run your code.
METHOD 1. The instructor opens a SAS file labeled clearly as the main *.sas file. Just before the header
comment block, there is just one %LET statement where the instructor specifies the folder. After changing
the folder, the instructor runs the entire file so that it defines whatever macros are needed and sets up
whatever new files or data sets are needed. Then the instructor opens a new SAS Editor window to type and
run invocations of the user-oriented flexible macro that accomplishes your assigned task.
METHOD 2. The instructor opens a SAS file labeled clearly as the main *.sas file and then runs the entire file
so that it defines whatever macros are needed and sets up whatever new files or data sets are needed. Then
the instructor opens a new SAS Editor window to type and run invocations of the user-oriented flexible
macro that accomplishes your assigned task. (For this method, one or more of your user-oriented macros
may need to request the instructor’s folder as one of its input parameters.)
Important Notes
• Your code should not automatically invoke the macro that provides the user flexibility, but it can invoke
macros used for setting up files and data sets.
• Your instructions should not require the user to select particular parts of your code to run. The user
should run your entire file at once to set up everything and then call your macro(s) on their own.
• Examples of the two methods above available. See the programs GradesOverTime_method1.sas and
GradesOverTime_method2.sas on Canvas.
Reminders on code presentation and documentation. Please include light comments throughout your code,
along with meaningful variable and dataset names, sensible indentation and spacing for readability, RUN/QUIT
statements for PROCs and DATA steps, and DATA= clauses in PROC statements. To avoid superfluous code,
please perform (wherever possible) multiple actions in a single PROC or DATA step rather than using multiple
PROC and DATA steps in sequence to perform a small number of adjustments. Please avoid repetitive or
redundant code by using macros, loops and/or arrays.